Indexing and retrieval medical images based on 2×2 DCT and IDS compression

Although digital images indexing and querying techniques have extensively been studied for the last years, few systems are dedicated to medical images today while the need for content-based analysis and retrieval tools increases with the growth of digital medical image databases. In this paper, we present a content based medical images indexing and retrieval technique (CBIR) using the 2×2 discrete cosine transform and information dominance strategy (IDS) compression. The extraction of the feature vectors is based on a 4×4 DCT model proposed in the literature. These features are directly generated from the 2×2 DCT coefficients reorganized in subbands and the search process is carried out: by´ calculating cosine distance measure between the signatures of the query image and those stored in the database. The developed 2×2 DCT approach is expected to be very useful for a targeted seeking.